Yufeng Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yufeng Chen has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Xiaoqian Zhang
Southwest University of Science and Technology
2 shared publications - Hao Pan1 shared publication
- Honglin Yuan
School of National Defence Science and Technology, Southwest University of Science and Technology, Mianyang, China
1 shared publication - Lifan Peng
Southwest University of Science and Technology, China
1 shared publication - Rong Tang
School of Information and Control Engineering, Southwest University of Science and Technology, Mianyang 621010, China
1 shared publication - Shijie Li
School of Information and Control Engineering, Southwest University of Science and Technology, Mianyang, 621010, China
1 shared publication
Latest Publications
- 14 March 2026
- Published by Elsevier in Pattern Recognition
- Vol. 178
Pixel intensity prior-aware balanced multi-modal image fusion
- 14 March 2026
- Published by Elsevier in Pattern Recognition
- Vol. 178
Pixel intensity prior-aware balanced multi-modal image fusion
- 23 October 2025
- Published by Elsevier in Neural Networks
- Vol. 195, 108230
DNUNet: A lightweight adaptive medical image segmentation network based on dual-path multilevel interactive convolution and norm sparse fusion module
- 23 October 2025
- Published by Elsevier in Neural Networks
- Vol. 195, 108230
DNUNet: A lightweight adaptive medical image segmentation network based on dual-path multilevel interactive convolution and norm sparse fusion module
- Open Access
- 15 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 120-125
Multi-view deep subspace clustering with multilevel self-representation matrix fusion
Currently, multi-view deep subspace clustering algorithms have achieved remarkable success. However, existing methods have not yet focused on comprehensive information mining within the deep encoder for clustering performance improvement. To this end, this paper presents a novel multi-view deep subspace clustering algorithm with multilevel self-representation matrix fusion. Specifically, the valid clustering information contained within the deep encoder is deeply mined by a multilevel self-representation matrix extraction module. At the same time, diversity and consistency constraints are used to differentiate the clustering information contained in the self-representation matrix (deep and shallow) for each view. Further, through the multilevel self-representation matrix fusion module, the various types of self-representation matrices are effectively fused: the deep and shallow self-representation matrices of each view and the consistency representation matrix to obtain a higher quality and more comprehensive self-representation coefficient matrix, which effectively improves the clustering performance. Experimental and visual analyses of four datasets show that the clustering performance of the proposed method is significantly better than some existing state-of-the-art methods.
- 15 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 120-125
Open AccessMulti-view deep subspace clustering with multilevel self-representation matrix fusion
Currently, multi-view deep subspace clustering algorithms have achieved remarkable success. However, existing methods have not yet focused on comprehensive information mining within the deep encoder for clustering performance improvement. To this end, this paper presents a novel multi-view deep subspace clustering algorithm with multilevel self-representation matrix fusion. Specifically, the valid clustering information contained within the deep encoder is deeply mined by a multilevel self-representation matrix extraction module. At the same time, diversity and consistency constraints are used to differentiate the clustering information contained in the self-representation matrix (deep and shallow) for each view. Further, through the multilevel self-representation matrix fusion module, the various types of self-representation matrices are effectively fused: the deep and shallow self-representation matrices of each view and the consistency representation matrix to obtain a higher quality and more comprehensive self-representation coefficient matrix, which effectively improves the clustering performance. Experimental and visual analyses of four datasets show that the clustering performance of the proposed method is significantly better than some existing state-of-the-art methods.